© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6965
    Prev
    Next
    INDEX
    Explanations

    code, writing, blueprint, equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ar
    1.29
     attract
    1.26
    شاركة
    1.25
    Select
    1.24
    1
    1.23
    Ar
    1.18
    Ad
    1.16
    Share
    1.14
     associ
    1.14
     gallery
    1.12
    POSITIVE LOGITS
    boiled
    1.76
    >>(
    1.76
    quina
    1.74
    }(-\
    1.73
    しろ
    1.73
     slaughtered
    1.72
     transcoding
    1.72
    laying
    1.71
    ıyordu
    1.70
    legg
    1.68
    Activations Density 0.013%

    No Known Activations